© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 85426
    Prev
    Next
    INDEX
    Explanations

    the word "also" in various contexts, indicating its focus on inclusion or addition of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     other
    -0.07
    other
    -0.07
    vers
    -0.06
     otras
    -0.06
     OTHER
    -0.06
     actually
    -0.06
     outras
    -0.06
    IBLE
    -0.06
    uart
    -0.06
     дÑĢÑĥгими
    -0.06
    POSITIVE LOGITS
     ebenfalls
    0.08
     ÑĤоже
    0.08
    erner
    0.08
     ìĹŃìĭľ
    0.08
    akit
    0.07
    eworld
    0.07
     váºŃy
    0.07
    ihu
    0.07
    arhus
    0.07
    lij
    0.07
    Activations Density 0.023%

    No Known Activations